Beyond Extractive Methods – Navigating the landscape of Abstractive Summarization Methods

Abstract

Today, millions of data are generated every hour, which highlights the need for summarizing all this data accurately and efficiently. Doing such a task manually is tedious. This welcomes the need for automatic summarizing techniques. Generating precise and concise summaries of long text data is a necessity. Automatic summarization includes two primary techniques- Extractive and Abstractive Summarization. Extractive Summarization uses important sentences and keywords to construct the summary whereas abstractive summarization understands the text and generates a summary. The encoder-decoder architecture is generally used for abstractive summarization. This study briefs about various transformer architectures, including T5, BART, and Pegasus. Furthermore, a comparative analysis of these models on the same data is presented and the result of the same is compared on scores with the manually generated summaries- ROUGE1, ROUGE2, and ROUGEL. The purpose of this study is to understand the advancement of abstractive text summarization models as well as to understand the strategies and their usefulness.